CN113762990A - Commodity recommendation method and device, computing equipment and computer storage medium - Google Patents

Commodity recommendation method and device, computing equipment and computer storage medium Download PDF

Info

Publication number
CN113762990A
CN113762990A CN202010493983.2A CN202010493983A CN113762990A CN 113762990 A CN113762990 A CN 113762990A CN 202010493983 A CN202010493983 A CN 202010493983A CN 113762990 A CN113762990 A CN 113762990A
Authority
CN
China
Prior art keywords
score
commodity
user
user preference
commodities
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010493983.2A
Other languages
Chinese (zh)
Other versions
CN113762990B (en
Inventor
柳淑婷
刘存
潘宇
骆似骏
黄文婷
吴逊
谢贤娟
杨俏
石益宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Group Zhejiang Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Group Zhejiang Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, China Mobile Group Zhejiang Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN202010493983.2A priority Critical patent/CN113762990B/en
Publication of CN113762990A publication Critical patent/CN113762990A/en
Application granted granted Critical
Publication of CN113762990B publication Critical patent/CN113762990B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G06Q30/0256—User search
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the invention relates to the technical field of big data, and discloses a method, a device, a computing device and a computer storage medium for commodity recommendation, wherein the method comprises the following steps: acquiring first characteristic data corresponding to each commodity under each heat factor; calculating the popularity score of each commodity under each popularity factor according to the first characteristic data; acquiring second characteristic data corresponding to each commodity under each user preference factor; calculating the user preference score of each commodity under each user preference factor according to the second characteristic data; carrying out weighted calculation on the popularity score and the user preference score to obtain a recommendation score of each commodity; and recommending the commodities according to the recommendation score. Through the mode, the embodiment of the invention realizes automatic commodity recommendation.

Description

Commodity recommendation method and device, computing equipment and computer storage medium
Technical Field
The embodiment of the invention relates to the technical field of big data, in particular to a commodity recommendation method, a commodity recommendation device, a computing device and a computer storage medium.
Background
To meet consumer shopping needs, retail establishments are gradually moving towards a "new retail" model. The new retail mode refers to a new efficient and convenient retail mode in which enterprises rely on the internet, and the production, circulation and sale processes of commodities are upgraded and modified by using advanced technical means such as big data, artificial intelligence and the like, so that the industrial structure and the ecological cycle are further reformed, and the online service and offline experience are deeply integrated.
Due to the limited space of the off-line stores, the sales staff need to select hot sales commodities suitable for the stores to be located from a large number of commodities for the stores to carry out marketing. At present, sales staff mainly check a large amount of sales record reports and inventory records and rely on abundant business experience to stock stores. The mode depends on the manual selection of hot-selling commodities from a large number of commodities by a sales staff, and the selection cost is high.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a method, an apparatus, a computing device, and a computer storage medium for recommending a commodity, so as to solve the problem in the prior art that the cost for manually selecting a hot-sold commodity is high.
According to an aspect of an embodiment of the present invention, there is provided a method of commodity recommendation, the method including:
acquiring first characteristic data corresponding to each commodity under each heat factor;
calculating the popularity score of each commodity under each popularity factor according to the first characteristic data;
acquiring second characteristic data corresponding to each commodity under each user preference factor;
calculating the user preference score of each commodity under each user preference factor according to the second characteristic data;
carrying out weighted calculation on the popularity score and the user preference score to obtain a recommendation score of each commodity;
and recommending the commodities according to the recommendation score.
In an optional mode, the heat factor comprises historical sales records, and the first characteristic data corresponding to the historical sales records comprises historical sales volume;
the calculating the popularity score of each commodity under each popularity factor according to the first characteristic data comprises the following steps:
sequencing the commodities according to the sequence of the historical sales from high to low to obtain sales ranks of the commodities;
and performing linear score distribution on the commodities according to the sales ranking to obtain the popularity score of each commodity in the historical sales record.
In an alternative mode, the user preference factor comprises a first preference of the store-entering user, and the second characteristic data corresponding to the first preference comprises a shopping list of the store-entering user;
the calculating the user preference score of each commodity under each user preference factor according to the second characteristic data comprises the following steps:
summarizing shopping lists of all store-entering users to obtain a shopping total list of the store-entering users, wherein the shopping total list comprises corresponding relations between commodities and purchase amounts;
sequencing the commodities according to the sequence of the purchase amount from top to bottom to obtain the purchase amount ranking of the commodities;
and performing linear score distribution according to the purchase amount ranking to obtain the user preference score of each commodity under the first preference.
In an alternative mode, the user preference factor comprises a second preference of an accessible user, and second feature data corresponding to the second preference comprises a search record of the accessible user, wherein the search record comprises a search keyword and a search frequency;
the calculating the user preference score of each commodity under each user preference factor according to the second characteristic data comprises the following steps:
calculating the similarity between each search keyword and the commodity name of each commodity;
taking the commodity with the highest similarity as the commodity corresponding to the search keyword;
counting the searching times of all accessible users for each commodity;
sorting according to the sequence of the searching times from high to low to obtain the searching ranking of each commodity;
and performing linear score distribution according to the search ranking to obtain the user preference score of each commodity under the second preference.
In an alternative mode, the user preference factor comprises a third preference of the inaccessible user, and the second feature data corresponding to the third preference comprises first user information of the accessible user and second user information of the inaccessible user;
the calculating the user preference score of each commodity under each user preference factor according to the second characteristic data comprises the following steps:
generating a corresponding feature vector according to the first user information and the second user information;
generating a plurality of cluster clusters by taking the feature vector corresponding to each second user information as a cluster center, wherein each cluster comprises one second user information and a plurality of first user information;
determining the scores of the commodities corresponding to the accessible users;
determining the scores of the inaccessible users on the commodities according to the scores of the accessible users on the commodities in the clustering clusters;
and calculating the average value of the scores of all the inaccessible users on the commodities to obtain the user preference score of each commodity under the third preference.
In an alternative mode, the weighting calculation of the popularity score and the user preference score to obtain the recommendation score of each commodity includes:
weighting and calculating the popularity score and the user preference score according to the initial weight value to obtain a first score of each commodity;
calculating a second score of each commodity according to the actual sales volume of each commodity;
adjusting the initial weight value according to the first score and the second score to obtain an adjusted weight value;
and carrying out weighted calculation on the popularity score and the user preference score according to the adjusted weight value to obtain the recommendation score of each commodity.
In an optional manner, after the item recommendation is made according to the recommendation score, the method further comprises:
determining the recommended ranks of the commodities;
and determining the goods intake according to the recommended rank.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for recommending a commodity, including:
the first acquisition module is used for acquiring first characteristic data corresponding to each commodity under each heat factor;
the first calculating module is used for calculating the popularity score of each commodity under each popularity factor according to the first characteristic data;
the second acquisition module is used for acquiring second characteristic data corresponding to each commodity under each user preference factor;
the second calculation module is used for calculating the user preference score of each commodity under each user preference factor according to the second characteristic data;
the third calculation module is used for carrying out weighted calculation on the popularity score and the user preference score to obtain a recommendation score of each commodity;
and the recommending module is used for recommending the commodities according to the recommending score.
According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the commodity recommending method.
According to another aspect of the embodiments of the present invention, there is provided a computer-readable storage medium having at least one executable instruction stored therein, where the executable instruction causes a computing device/apparatus to perform operations corresponding to the above-mentioned method for recommending an article.
The embodiment of the invention calculates and obtains the popularity score of each commodity under each popularity factor and the user preference score of each commodity under each user preference factor, carries out weighting calculation on each popularity score and each user preference score of each commodity to obtain the recommendation score of each commodity, and carries out commodity recommendation according to the recommendation score of each commodity. By the embodiment of the invention, commodity recommendation can be automatically realized, and the cost of human resources is saved; in addition, the commodity recommended in the embodiment of the invention comprehensively considers the popularity factor of the commodity and the preference of the user, so that the recommended commodity is more accurate.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for merchandise recommendation provided by an embodiment of the invention;
FIG. 2 is a flowchart illustrating a calculation of a user preference score of an incoming user in a method for recommending goods according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a calculation of a user preference score of an accessible user in a method for merchandise recommendation according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a calculation of a user preference score of an inaccessible user in a method for recommending goods according to an embodiment of the present invention;
FIG. 5 is a functional block diagram of an apparatus for merchandise recommendation provided by an embodiment of the present invention;
fig. 6 shows a schematic structural diagram of a computing device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein.
The application scenario of the embodiment of the invention is commodity recommendation of a new retail store. The new retail store may make both off-line sales and on-line sales. The commodity recommendation in the embodiment of the invention is used for automatically recommending hot-sold commodities for a new retail store, so that the problem of high cost caused by the fact that hot-sold commodities need to be manually selected from massive commodities in the prior art is solved. The following describes embodiments of the present invention.
Fig. 1 shows a flowchart of a method for recommending goods according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
step 110: and acquiring first characteristic data corresponding to each commodity under each heat factor.
Each of the commodities may be a part of the commodities in a new retail store, or may be all of the commodities in a new retail store. When the embodiment of the invention is applied to different fields, the types of commodities are commodities in corresponding fields. For example, when the embodiments of the present invention are applied to the field of communications, commodities are various specific services. The heat factor is a factor related to the sales volume of the commercial product. In the embodiment of the invention, the heat factors comprise historical sales records, cloud shelf click browsing records and electronic price tag code scanning browsing records. The time dimensions corresponding to the historical sales records, the cloud shelf click browsing records and the electronic price tag code scanning browsing records are the same. The time dimension may be the time since the establishment of the new retail store or a predetermined time period. The first characteristic data corresponding to the historical sales records comprise historical sales volume of each commodity; the first characteristic data corresponding to the cloud shelf click browsing record comprises the click quantity of each commodity, and the electronic price tag code scanning browsing record comprises the code scanning quantity of each commodity.
Step 120: and calculating the popularity score of each commodity under each popularity factor according to the first characteristic data.
The calculation rules of the popularity score of each commodity under each popularity factor can be the same or different. Preferably, the calculation rules of the heat score of each commodity under each heat factor are the same, and the same calculation rule can be used for calculating the heat score of each commodity under each heat factor, so that the calculation efficiency is improved. Taking the historical sales record as an example, the calculation rule for calculating the popularity score of each commodity according to the historical sales amount is as follows: sequencing the commodities according to the historical sales in the order from top to bottom to obtain sales ranks of the commodities; and performing linear score distribution on the commodities according to sales ranking to obtain the popularity score of each commodity in the historical sales records. Taking three commodities A, B, C as an example, the sales ranking of each commodity obtained by ranking according to the historical sales is B, A, C, assuming that the full hot score is 10 points, the hot score of the first commodity in the ranking is 10 points, the hot score of the last commodity in the ranking is 0 point, and the hot scores of the intermediate commodities are arranged linearly. The heat score of the commodity B is 10 points, the heat score of the commodity a is 5 points, and the heat score of the commodity C is 0 point.
In some embodiments, there is a case where the sales amount of a plurality of commodities is the same, and in this case, the commodities having the same sales amount are linearly arranged as the same commodity. For example, when the product A, B, C, D is sold in the order of sales, B is the highest sales, C is the lowest sales, and A and D are the same sales and are juxtaposed in the second place. The heat score of the commodity B is 10 points, the heat score of the commodity C is 0 point, and the heat scores of the commodity A and the commodity D are both 5 points.
Step 130: and acquiring second characteristic data corresponding to each commodity under each user preference factor.
The user preference factors include the preference factors of the store-entering user, the preference factors of the surrounding users, the preference factors of the accessible users and the preference factors of the inaccessible users. The preference factors of the store-entering user refer to users entering a new retail store, including users entering a physical store and users entering an online store. The peripheral users refer to users around the store, and specifically, users within a preset range of the store. For example, users within 1.5 km of a store are peripheral users. The accessible user refers to a user who can obtain online store searching and browsing records; an inaccessible user refers to a user that is associated with a new retail store but cannot acquire online store search and browsing records, e.g., a member of the new retail store that cannot access the user search and browse records.
The second characteristic data corresponding to the preference of the store-entering user is a shopping list of the store-entering user; the second characteristic data corresponding to the preferences of the surrounding users is shopping lists of the surrounding users. The shopping list is all shopping lists of each store-entering user in a period of time. The second characteristic data of the accessible users is search records of the accessible users, wherein the search records comprise search keywords and search times. The second characteristic data of the inaccessible user includes first user information of the accessible user and second user information of the inaccessible user. The first user information and the second user information have the same dimension, and when the embodiment of the invention is applied to the communication field, the first user information and the second user information both comprise: age, gender, first six digits of an identity card, monthly average call times in a first time period, monthly average flow, terminal price, whether to order broadband or not, whether to order broadband television or not, frequency of changing machines in a second time period, quality of a circle of contact, whether to have a car, marital status, occupation and other information. The age, the monthly average call times in the first time period, the monthly average flow, the terminal price, the frequency of changing the machine in the second time period and the quality of the contact circle are interval type data, the gender, whether to order the broadband television, whether to have a vehicle as binary data, and the rest information is coded data.
Step 140: and calculating the user preference score of each commodity under each user preference factor according to the second characteristic data.
In this step, the corresponding method for calculating the user preference score is different according to different user preference factors. For the first preference of the store-entering user, the corresponding second feature data is the shopping list of the store-entering user, and the calculation method of the corresponding user preference score is shown in fig. 2. Fig. 2 shows a flowchart of a user preference score corresponding to a store-entering user, which specifically includes the following steps:
step 210: and summarizing shopping lists of all store-entering users to obtain a shopping total list of the store-entering users, wherein the shopping total list comprises the corresponding relation between the commodities and the purchase quantity.
And sorting and summarizing all shopping lists of all users according to the names of the commodities to obtain the purchase quantity of each commodity.
Step 220: and sequencing the commodities according to the sequence of the purchase quantity from high to low to obtain the purchase quantity ranking of the commodities.
Step 230: the linear score assignment is performed in accordance with the purchase amount ranking to obtain a user preference score for each item at the first preference.
The first commodity score in the purchase amount ranking is full score, the last commodity score is zero score, and the rest commodities are linearly distributed. The linear distribution method may refer to the calculation method of the heat score in step 120, which is not described herein.
In some embodiments, there is a case where the purchase amount of a plurality of commodities is zero, and in this case, when performing linear score distribution, linear score distribution is performed by regarding all commodities whose purchase amount is zero as one commodity. For example, the purchase amount of the commercial product A, B, C, D, E, F is ranked as BCFADE, wherein the purchase amount of F, A, D, E is zero, and if the full score is 10 points, then when linear score allocation is performed, the user preference score of F, A, D, E is 0 point, the user preference score of B is 10 points, and the user preference score of C is 5 points.
The preference score of the surrounding user is the same as the calculation method of the preference score of the store-entering user, please refer to the calculation method of the preference score of the store-entering user in fig. 2, which is not described herein.
The second user accessible characteristic data includes a search record of the user accessible, the search record including a search keyword and a number of searches. The calculation method of the accessible user preference score is shown in fig. 3, and specifically comprises the following steps:
step 310: and calculating the similarity between each search keyword and the commodity name of each commodity.
The search keywords and the commodity names may not be in one-to-one correspondence, so the association degree between the search keywords and the commodity names is measured by calculating the semantic similarity between texts. The specific calculation flow comprises the following steps: preprocessing each search keyword and each commodity name respectively to obtain a corresponding datamation structure; and constructing a word2vec Chinese model to calculate word similarity. The word2vec Chinese model is a neural probability language model, and the model takes public texts such as Baidu encyclopedia and the like as a corpus to train the word2vec language model. After the model is trained, the similarity between the data structure corresponding to the search keyword and the data structure corresponding to the commodity name is calculated through the similarity calculation package in the model.
Step 320: and taking the commodity with the highest similarity as the commodity corresponding to the search keyword.
Wherein, the similarity between each search keyword and the commodity name of each commodity is obtained through the calculation method in step 310. The product name with the highest similarity is referred to as a product corresponding to the search keyword.
Step 330: and counting the searching times of all accessible users for each commodity.
And taking the commodity with the highest similarity with each search keyword as the commodity which can be searched by the user. And summarizing all the commodities which can be searched by the accessible users according to the names of the commodities to obtain the searching times corresponding to each commodity.
Step 340: and sequencing according to the sequence of the searching times from high to low to obtain the searching ranking of each commodity.
Step 350: and performing linear score distribution according to the search ranking to obtain the user preference score of each commodity under the second preference.
The second characteristic data of the inaccessible user includes first user information of the accessible user and second user information of the inaccessible user. The preference score is calculated as shown in fig. 4, and specifically includes the following steps:
step 410: and generating a corresponding feature vector according to the first user information and the second user information.
The feature vector comprises a plurality of dimensions, and each dimension corresponds to one type of user information. The interval type information may digitally encode each interval, and determine a corresponding value according to the interval to which each specific information belongs. For example, if there are three sections [ a, b), [ b, c), [ c, d), the three sections are encoded by 1, 2, 3, respectively, and if one piece of information belongs to [ b, c), the corresponding encoding of the information is 2. The binary data takes a value of 0 or 1, for example, for whether or not the broadband information is ordered, when the broadband is ordered, the corresponding code is 1, and when the broadband is not ordered, the corresponding code is 0. For the encoding type data, corresponding codes can be respectively established according to the categories. For example, for the marital status, unmarried, married, divorced, and wife are represented by the numbers 1, 2, 3, and 4, respectively, and values are taken in the dimensions corresponding to the marital status in the feature vector according to specific information.
Step 420: and generating a plurality of cluster clusters by taking the characteristic vector corresponding to each second user information as a cluster center.
And the clustering cluster is generated according to the Euclidean distance between the characteristic vector corresponding to each second user information and the characteristic vector corresponding to each first user information. The number of the cluster clusters is the same as the number of the second user information. Each cluster comprises a feature vector corresponding to the second user information and a plurality of feature vectors corresponding to the first user information. Specifically, the euclidean distance between the second feature vector corresponding to each piece of second user information and the second feature vector corresponding to each piece of first user information is calculated to obtain a plurality of euclidean distances corresponding to each piece of second user information. And taking the k pieces of first user information with the minimum distance in all Euclidean distances corresponding to one piece of second user information as the first user information of the same cluster with the second user information.
Step 430: and determining the scores of the commodities corresponding to the accessible users.
And the scores of the commodities corresponding to the accessible users are obtained according to the number of times of searching each commodity by the accessible users. Specifically, the product corresponding to each search keyword is obtained according to the method from step 310 to step 320. And summarizing all the commodities searched by all the accessible users, ranking according to the searching times, and performing linear score distribution according to the ranking from high to low to obtain the scores of all the commodities of all the accessible users.
Step 440: and determining the scores of the inaccessible users on the commodities according to the scores of the accessible users on the commodities in the clustering clusters.
And calculating the average value of the scores of the accessible users in the same cluster on the commodities according to the categories of the commodities, and taking the average value as the score of the inaccessible users in the cluster on the commodities. For example, if a cluster includes one inaccessible user and three accessible users, and the scores of items A, B, C by the three accessible users are (10, 6, 2), (8, 0, 1) and (0, 6, 3), respectively, then the scores of items A, B, C by the inaccessible users in the cluster are (6, 4, 2), respectively.
In some embodiments, the predictive score for item a by inaccessible user U is calculated according to the following formula:
Figure BDA0002522091560000101
wherein, UiIs the ith accessible user s in the same cluster with the inaccessible user UiFor accessible users UiThe score for the commercial product a was determined,
Figure BDA0002522091560000102
scoring the commodity A for all accessible users in the cluster, dist is the inaccessible user U and the accessible user UiThe euclidean distance between them,
Figure BDA0002522091560000103
is the average distance between the inaccessible user U and all accessible users; the calculation formula of the Euclidean distance is as follows:
Figure BDA0002522091560000111
wherein j represents j-th dimension information, and x and y represent inaccessible user U and accessible user U, respectivelyiThe j-th dimension of (1).
Step 450: and calculating the average value of the scores of all the inaccessible users on the commodities to obtain the user preference score of each commodity under the third preference.
And calculating the average value of the scores of the inaccessible users in each cluster on each commodity according to the commodity category to obtain the user preference score of each commodity under the third preference.
Step 150: and carrying out weighted calculation on the popularity score and the user preference score to obtain the recommendation score of each commodity.
In this step, the popularity score under each popularity factor and the user preference score under each user preference factor are weighted to obtain the recommendation score of each commodity. Wherein, the weight corresponding to each heat factor and each user preference factor is preset.
In some embodiments, each preset weight is modified based on the actual sales of each product over the last period of time.Specifically, weighting calculation is carried out on the popularity score and the user preference score according to the initial weight value, and a first score of each commodity is obtained; calculating a second score of each commodity according to the actual sales volume of each commodity; adjusting the initial weight value according to the first score and the second score to obtain an adjusted weight value; and carrying out weighted calculation again on the popularity score and the user preference score according to the adjusted weight value to obtain the recommendation score of each commodity. Wherein, the first score is obtained by calculation according to a preset initial weight value, and the calculation formula is
Figure BDA0002522091560000112
Wherein N represents the total number of heat factors and user preference factors, xtRepresenting the t-th heat factor or user preference factor, wtAre the corresponding weights. According to the formula
Figure BDA0002522091560000113
Where m represents the actual sales volume of the mth product, and salelmax represents the actual sales volume of the product with the highest sales volume among all the products. The full score is the score of the item with the highest sales, for example, 10, and then 10. In adjusting the initial values of the weights, the adjustment is performed by a multiple linear regression algorithm, and the adjustment is performed to minimize the difference between score2 and score 1.
Step 160: and recommending the commodities according to the recommendation score.
Wherein, the commodity recommendation is performed according to the sequence of the recommendation score from high to low.
The embodiment of the invention calculates and obtains the popularity score of each commodity under each popularity factor and the user preference score of each commodity under each user preference factor, carries out weighting calculation on each popularity score and each user preference score of each commodity to obtain the recommendation score of each commodity, and carries out commodity recommendation according to the recommendation score of each commodity. By the embodiment of the invention, commodity recommendation can be automatically realized, and the cost of human resources is saved; in addition, the commodity recommended in the embodiment of the invention comprehensively considers the popularity factor of the commodity and the preference of the user, so that the recommended commodity is more accurate.
In some embodiments, after step 150, a recommended ranking for each item is determined; and determining the goods intake according to the recommended rank. When the goods quantity is determined according to the recommended rank, the commodity sales quantity, the store inventory quantity, the goods input price and the average inventory quantity of all the commodities in the store in the last week are referred to at the same time. In one embodiment, the specific inventory calculation is as shown in Table 1 below:
TABLE 1
Figure BDA0002522091560000121
Wherein D ismaxRepresenting the largest ranking of all the items, e.g. a total of 50 items, with ranks 1 to 50, respectively, Dmax50. By the method, the commodity quantity of each commodity in the new retail store is automatically calculated, the human resource cost is saved, and the operation efficiency of the new retail store is improved.
Fig. 5 shows a functional block diagram of an apparatus for recommending merchandise according to an embodiment of the present invention. As shown in fig. 5, the apparatus includes: a first obtaining module 510, a first calculating module 520, a second obtaining module 530, a second calculating module 540, a third calculating module 550, and a recommending module 560.
The first obtaining module 510 is configured to obtain first feature data corresponding to each commodity under each heat factor;
the first calculating module 520 is used for calculating the popularity score of each commodity under each popularity factor according to the first characteristic data;
the second obtaining module 530 is configured to obtain second feature data corresponding to each commodity under each user preference factor;
the second calculating module 540 is used for calculating the user preference score of each commodity under each user preference factor according to the second characteristic data;
the third calculating module 550 is configured to perform weighted calculation on the popularity score and the user preference score to obtain a recommendation score of each item;
and the recommending module 560 is used for recommending commodities according to the recommendation scores.
In an optional mode, the heat factor comprises historical sales records, and the first characteristic data corresponding to the historical sales records comprises historical sales volume;
the first calculation module 520 is further configured to:
sequencing the commodities according to the sequence of the historical sales from high to low to obtain sales ranks of the commodities;
and performing linear score distribution on the commodities according to the sales ranking to obtain the popularity score of each commodity in the historical sales record.
In an alternative mode, the user preference factor comprises a first preference of the store-entering user, and the second characteristic data corresponding to the first preference comprises a shopping list of the store-entering user;
the second computing module 540 is further configured to:
summarizing shopping lists of all store-entering users to obtain a shopping total list of the store-entering users, wherein the shopping total list comprises corresponding relations between commodities and purchase amounts;
sequencing the commodities according to the sequence of the purchase amount from top to bottom to obtain the purchase amount ranking of the commodities;
and performing linear score distribution according to the purchase amount ranking to obtain the user preference score of each commodity under the first preference.
In an alternative mode, the user preference factor comprises a second preference of an accessible user, and second feature data corresponding to the second preference comprises a search record of the accessible user, wherein the search record comprises a search keyword and a search frequency;
the second computing module 540 is further configured to:
calculating the similarity between each search keyword and the commodity name of each commodity;
taking the commodity with the highest similarity as the commodity corresponding to the search keyword;
counting the searching times of all accessible users for each commodity;
sorting according to the sequence of the searching times from high to low to obtain the searching ranking of each commodity;
and performing linear score distribution according to the search ranking to obtain the user preference score of each commodity under the second preference.
In an alternative mode, the user preference factor comprises a third preference of the inaccessible user, and the second feature data corresponding to the third preference comprises first user information of the accessible user and second user information of the inaccessible user;
the second computing module 540 is further configured to:
generating a corresponding feature vector according to the first user information and the second user information;
generating a plurality of cluster clusters by taking the feature vector corresponding to each second user information as a cluster center, wherein each cluster comprises one second user information and a plurality of first user information;
determining the scores of the commodities corresponding to the accessible users;
determining the scores of the inaccessible users on the commodities according to the scores of the accessible users on the commodities in the clustering clusters;
and calculating the average value of the scores of all the inaccessible users on the commodities to obtain the user preference score of each commodity under the third preference.
In an optional manner, the third calculating module 550 is further configured to:
weighting and calculating the popularity score and the user preference score according to the initial weight value to obtain a first score of each commodity;
calculating a second score of each commodity according to the actual sales volume of each commodity;
adjusting the initial weight value according to the first score and the second score to obtain an adjusted weight value;
and carrying out weighted calculation on the popularity score and the user preference score according to the adjusted weight value to obtain the recommendation score of each commodity.
In an optional manner, the apparatus further comprises: a first determination module 570 and a second determination module 580, the first determination module 570 being used to determine a recommended ranking for each item. The second determination module 580 is for determining the amount of the shipment based on the recommended line.
The embodiment of the invention calculates and obtains the popularity score of each commodity under each popularity factor and the user preference score of each commodity under each user preference factor, carries out weighting calculation on each popularity score and each user preference score of each commodity to obtain the recommendation score of each commodity, and carries out commodity recommendation according to the recommendation score of each commodity. By the embodiment of the invention, commodity recommendation can be automatically realized, and the cost of human resources is saved; in addition, the commodity recommended in the embodiment of the invention comprehensively considers the popularity factor of the commodity and the preference of the user, so that the recommended commodity is more accurate.
Fig. 6 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 6, the computing device may include: a processor (processor)602, a communication Interface 604, a memory 606, and a communication bus 608.
Wherein: the processor 602, communication interface 604, and memory 606 communicate with one another via a communication bus 608. A communication interface 604 for communicating with network elements of other devices, such as clients or other servers. The processor 602 is configured to execute the program 610, and may specifically perform relevant steps in the above method embodiment for recommending a commodity.
In particular, program 610 may include program code comprising computer-executable instructions.
The processor 602 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 606 for storing a program 610. Memory 606 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Specifically, program 610 may be invoked by processor 602 to cause a computing device to perform steps 110 to 160 in fig. 1, steps 210 to 230 in fig. 2, steps 310 to 350 in fig. 3, and steps 410 to 450 in fig. 4, and to implement the functions of modules 510 to 580 in fig. 5.
An embodiment of the present invention provides a computer-readable storage medium, where the storage medium stores at least one executable instruction, and when the executable instruction is executed on a computing device/apparatus, the computing device/apparatus is caused to execute a method for recommending a product in any of the above method embodiments.
Embodiments of the present invention provide a computer program, where the computer program can be called by a processor to enable a computing device to execute a method for recommending a commodity in any of the above method embodiments.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions that, when run on a computer, cause the computer to perform a method of merchandise recommendation in any of the method embodiments described above.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims (10)

1. A method of merchandise recommendation, the method comprising:
acquiring first characteristic data corresponding to each commodity under each heat factor;
calculating the popularity score of each commodity under each popularity factor according to the first characteristic data;
acquiring second characteristic data corresponding to each commodity under each user preference factor;
calculating the user preference score of each commodity under each user preference factor according to the second characteristic data;
carrying out weighted calculation on the popularity score and the user preference score to obtain a recommendation score of each commodity;
and recommending the commodities according to the recommendation score.
2. The method of claim 1, wherein the heat factor comprises historical sales records, and the first characteristic data corresponding to the historical sales records comprises historical sales volume;
the calculating the popularity score of each commodity under each popularity factor according to the first characteristic data comprises the following steps:
sequencing the commodities according to the sequence of the historical sales from high to low to obtain sales ranks of the commodities;
and performing linear score distribution on the commodities according to the sales ranking to obtain the popularity score of each commodity in the historical sales record.
3. The method of claim 1, wherein the user preference factor comprises a first preference of an in-store user, and wherein the second characteristic data corresponding to the first preference comprises a shopping list of the in-store user;
the calculating the user preference score of each commodity under each user preference factor according to the second characteristic data comprises the following steps:
summarizing shopping lists of all store-entering users to obtain a shopping total list of the store-entering users, wherein the shopping total list comprises corresponding relations between commodities and purchase amounts;
sequencing the commodities according to the sequence of the purchase amount from top to bottom to obtain the purchase amount ranking of the commodities;
and performing linear score distribution according to the purchase amount ranking to obtain the user preference score of each commodity under the first preference.
4. The method of claim 1, wherein the user preference factors include a second preference of the accessible user, wherein the second feature data corresponding to the second preference includes a search record of the accessible user, wherein the search record includes a search keyword and a search number;
the calculating the user preference score of each commodity under each user preference factor according to the second characteristic data comprises the following steps:
calculating the similarity between each search keyword and the commodity name of each commodity;
taking the commodity with the highest similarity as the commodity corresponding to the search keyword;
counting the searching times of all accessible users for each commodity;
sorting according to the sequence of the searching times from high to low to obtain the searching ranking of each commodity;
and performing linear score distribution according to the search ranking to obtain the user preference score of each commodity under the second preference.
5. The method of claim 1, wherein the user preference factors include third preferences of the inaccessible user, and wherein the second feature data corresponding to the third preferences includes first user information of the accessible user and second user information of the inaccessible user;
the calculating the user preference score of each commodity under each user preference factor according to the second characteristic data comprises the following steps:
generating a corresponding feature vector according to the first user information and the second user information;
generating a plurality of cluster clusters by taking the feature vector corresponding to each second user information as a cluster center, wherein each cluster comprises one second user information and a plurality of first user information;
determining the scores of the commodities corresponding to the accessible users;
determining the scores of the inaccessible users on the commodities according to the scores of the accessible users on the commodities in the clustering clusters;
and calculating the average value of the scores of all the inaccessible users on the commodities to obtain the user preference score of each commodity under the third preference.
6. The method of claim 1, wherein the weighting the popularity score and the user preference score to obtain a recommendation score for each item comprises:
weighting and calculating the popularity score and the user preference score according to the initial weight value to obtain a first score of each commodity;
calculating a second score of each commodity according to the actual sales volume of each commodity;
adjusting the initial weight value according to the first score and the second score to obtain an adjusted weight value;
and carrying out weighted calculation on the popularity score and the user preference score according to the adjusted weight value to obtain the recommendation score of each commodity.
7. The method of claim 1, wherein after the recommendation of the item according to the recommendation score, the method further comprises:
determining the recommended ranks of the commodities;
and determining the goods intake according to the recommended rank.
8. An apparatus for merchandise recommendation, the apparatus comprising:
the first acquisition module is used for acquiring first characteristic data corresponding to each commodity under each heat factor;
the first calculating module is used for calculating the popularity score of each commodity under each popularity factor according to the first characteristic data;
the second acquisition module is used for acquiring second characteristic data corresponding to each commodity under each user preference factor;
the second calculation module is used for calculating the user preference score of each commodity under each user preference factor according to the second characteristic data;
the third calculation module is used for carrying out weighted calculation on the popularity score and the user preference score to obtain a recommendation score of each commodity;
and the recommending module is used for recommending the commodities according to the recommending score.
9. A computing device, wherein the computing device comprises: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the corresponding operation of the commodity recommendation method according to any one of claims 1-7.
10. A computer-readable storage medium, wherein the storage medium has at least one executable instruction stored therein, and the executable instruction when executed on a computing device/apparatus causes the computing device/apparatus to perform operations corresponding to a method for recommending goods according to any one of claims 1-7.
CN202010493983.2A 2020-06-03 2020-06-03 Commodity recommendation method, commodity recommendation device, computing equipment and computer storage medium Active CN113762990B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010493983.2A CN113762990B (en) 2020-06-03 2020-06-03 Commodity recommendation method, commodity recommendation device, computing equipment and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010493983.2A CN113762990B (en) 2020-06-03 2020-06-03 Commodity recommendation method, commodity recommendation device, computing equipment and computer storage medium

Publications (2)

Publication Number Publication Date
CN113762990A true CN113762990A (en) 2021-12-07
CN113762990B CN113762990B (en) 2024-03-22

Family

ID=78783150

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010493983.2A Active CN113762990B (en) 2020-06-03 2020-06-03 Commodity recommendation method, commodity recommendation device, computing equipment and computer storage medium

Country Status (1)

Country Link
CN (1) CN113762990B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081956A (en) * 2022-08-16 2022-09-20 杭州比智科技有限公司 Intelligent client visiting method and system based on building two-reach graph

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663627A (en) * 2012-04-26 2012-09-12 焦点科技股份有限公司 Personalized recommendation method
US20140279208A1 (en) * 2013-03-14 2014-09-18 Rosie Electronic shopping system and service
JP2015014887A (en) * 2013-07-04 2015-01-22 株式会社東芝 Commodity information provision system, commodity information provision method, server and program
CN105469263A (en) * 2014-09-24 2016-04-06 阿里巴巴集团控股有限公司 Commodity recommendation method and device
KR20160065429A (en) * 2014-11-30 2016-06-09 주식회사 알티웍스 Hybrid personalized product recommendation method
CN107194769A (en) * 2017-05-17 2017-09-22 东莞市华睿电子科技有限公司 A kind of Method of Commodity Recommendation that content is searched for based on user
CN107274242A (en) * 2016-04-08 2017-10-20 上海旭薇物联网科技有限公司 A kind of Method of Commodity Recommendation based on association analysis algorithm
CN107888950A (en) * 2017-11-09 2018-04-06 福州瑞芯微电子股份有限公司 A kind of method and system for recommending video
CN107944913A (en) * 2017-11-21 2018-04-20 重庆邮电大学 High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis
CN108009897A (en) * 2017-12-25 2018-05-08 北京中关村科金技术有限公司 A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing
CN108805622A (en) * 2018-06-11 2018-11-13 深圳乐信软件技术有限公司 Method of Commodity Recommendation, device, equipment and storage medium
CN108876526A (en) * 2018-06-06 2018-11-23 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device and computer readable storage medium
CN108960945A (en) * 2017-05-18 2018-12-07 北京京东尚科信息技术有限公司 Method of Commodity Recommendation and device
CN109189904A (en) * 2018-08-10 2019-01-11 上海中彦信息科技股份有限公司 Individuation search method and system
CN109410004A (en) * 2018-10-29 2019-03-01 维沃移动通信有限公司 A kind of recommended method, device and mobile terminal
CN109919728A (en) * 2019-03-12 2019-06-21 贵州大学 A kind of Method of Commodity Recommendation in difference quotient city
CN110084671A (en) * 2019-04-17 2019-08-02 上海拉扎斯信息科技有限公司 Information processing method, information processing unit, storage medium and electronic equipment

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663627A (en) * 2012-04-26 2012-09-12 焦点科技股份有限公司 Personalized recommendation method
US20140279208A1 (en) * 2013-03-14 2014-09-18 Rosie Electronic shopping system and service
JP2015014887A (en) * 2013-07-04 2015-01-22 株式会社東芝 Commodity information provision system, commodity information provision method, server and program
CN105469263A (en) * 2014-09-24 2016-04-06 阿里巴巴集团控股有限公司 Commodity recommendation method and device
KR20160065429A (en) * 2014-11-30 2016-06-09 주식회사 알티웍스 Hybrid personalized product recommendation method
CN107274242A (en) * 2016-04-08 2017-10-20 上海旭薇物联网科技有限公司 A kind of Method of Commodity Recommendation based on association analysis algorithm
CN107194769A (en) * 2017-05-17 2017-09-22 东莞市华睿电子科技有限公司 A kind of Method of Commodity Recommendation that content is searched for based on user
CN108960945A (en) * 2017-05-18 2018-12-07 北京京东尚科信息技术有限公司 Method of Commodity Recommendation and device
CN107888950A (en) * 2017-11-09 2018-04-06 福州瑞芯微电子股份有限公司 A kind of method and system for recommending video
CN107944913A (en) * 2017-11-21 2018-04-20 重庆邮电大学 High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis
CN108009897A (en) * 2017-12-25 2018-05-08 北京中关村科金技术有限公司 A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing
CN108876526A (en) * 2018-06-06 2018-11-23 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device and computer readable storage medium
CN108805622A (en) * 2018-06-11 2018-11-13 深圳乐信软件技术有限公司 Method of Commodity Recommendation, device, equipment and storage medium
CN109189904A (en) * 2018-08-10 2019-01-11 上海中彦信息科技股份有限公司 Individuation search method and system
CN109410004A (en) * 2018-10-29 2019-03-01 维沃移动通信有限公司 A kind of recommended method, device and mobile terminal
CN109919728A (en) * 2019-03-12 2019-06-21 贵州大学 A kind of Method of Commodity Recommendation in difference quotient city
CN110084671A (en) * 2019-04-17 2019-08-02 上海拉扎斯信息科技有限公司 Information processing method, information processing unit, storage medium and electronic equipment

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
于奕;: "基于用户预测的推荐算法研究", 电脑编程技巧与维护, no. 18, pages 66 *
李峰;李军怀;王瑞林;张;: "基于商品特征的个性化推荐算法", 计算机工程与应用, no. 17, pages 194 - 197 *
陈鑫等: "商品搭配大数据推荐方法研究综述", 《计算机工程与科学》, vol. 42, no. 01, pages 36 - 45 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081956A (en) * 2022-08-16 2022-09-20 杭州比智科技有限公司 Intelligent client visiting method and system based on building two-reach graph

Also Published As

Publication number Publication date
CN113762990B (en) 2024-03-22

Similar Documents

Publication Publication Date Title
US11257049B1 (en) Item identification based on receipt image
CN108960945A (en) Method of Commodity Recommendation and device
US8694372B2 (en) Systems and methods for automatic control of marketing actions
CN107220852A (en) Method, device and server for determining target recommended user
CN107247786A (en) Method, device and server for determining similar users
CN107808314B (en) User recommendation method and device
CA2655196A1 (en) System and method for generating a display of tags
US11321724B1 (en) Product evaluation system and method of use
CN111428007B (en) Cross-platform based synchronous push feedback method
US11200593B2 (en) Predictive recommendation system using tiered feature data
CN105630836A (en) Searching result sorting method and apparatus
US11841905B2 (en) Attribute node widgets in search results from an item graph
CN107093122B (en) Object classification method and device
US20240161163A1 (en) Query reformulations for an item graph
CN113762990B (en) Commodity recommendation method, commodity recommendation device, computing equipment and computer storage medium
CN110020918B (en) Recommendation information generation method and system
CN112036987A (en) Method and device for determining recommended commodities
KR102576123B1 (en) Product marketing linkage system and method
KR20230072097A (en) System and method for recommending product based on rate of return
Hung Using Cloud Services to Develop Marketing Information System Applications
CN110020136B (en) Object recommendation method and related equipment
CN111400622A (en) Method and device for showing quantity of short-lived commodities in distributed e-commerce system
US20240232406A9 (en) Storing and retrieving data based on experience in categories associated with historical interactions
US20240104622A1 (en) Boosting scores for ranking items matching a search query
US20230099904A1 (en) Machine learning model prediction of interest in an object

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant